vercel-automation
Fail
Audited by Snyk on Feb 20, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The prompt requires creating environment variables with a 'value' parameter (including secret type vars), which implies the agent must accept and include secret values verbatim in tool calls/requests, creating an exfiltration risk.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires adding and calling the external MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch current tool schemas that directly determine available tools/instructions, so this external content can control agent behavior.
Audit Metadata